Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4073 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.3578. Min Act: -0.0000

Data Index: 1405635 (Python Code)

Max Activating Token Index: 825

Text #1

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1587571 (Python Code)

Max Activating Token Index: 704

Text #2

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1447479 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1593706 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1553763 (Python Code)

Max Activating Token Index: 427

Text #5

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1555700 (Python Code)

Max Activating Token Index: 837

Text #6

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1510260 (Python Code)

Max Activating Token Index: 65

Text #7

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1457203 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1625639 (Python Code)

Max Activating Token Index: 596

Text #9

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1363000 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1596454 (Python Code)

Max Activating Token Index: 393

Text #11

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7060. Min Act: 0.0000

Data Index: 1503258 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6547. Min Act: -0.0000

Data Index: 236649 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7063. Min Act: 0.0000

Data Index: 1482603 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1555741 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1388033 (Python Code)

Max Activating Token Index: 1016

Text #16

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1426387 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1474507 (Python Code)

Max Activating Token Index: 807

Text #18

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6654. Min Act: 0.0000

Data Index: 1547741 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1549813 (Python Code)

Max Activating Token Index: 580